1 |
6daefa8c
|
Petr Lukašík
|
<?php
|
2 |
|
|
/* SVN FILE: $Id: flay.php 4409 2007-02-02 13:20:59Z phpnut $ */
|
3 |
|
|
/**
|
4 |
|
|
* Text-to-HTML parser.
|
5 |
|
|
*
|
6 |
|
|
* Text-to-html parser, similar to {@link http://textism.com/tools/textile/ Textile} or {@link http://www.whytheluckystiff.net/ruby/redcloth/ RedCloth}.
|
7 |
|
|
*
|
8 |
|
|
* PHP versions 4 and 5
|
9 |
|
|
*
|
10 |
|
|
* CakePHP(tm) : Rapid Development Framework <http://www.cakephp.org/>
|
11 |
|
|
* Copyright 2005-2007, Cake Software Foundation, Inc.
|
12 |
|
|
* 1785 E. Sahara Avenue, Suite 490-204
|
13 |
|
|
* Las Vegas, Nevada 89104
|
14 |
|
|
*
|
15 |
|
|
* Licensed under The MIT License
|
16 |
|
|
* Redistributions of files must retain the above copyright notice.
|
17 |
|
|
*
|
18 |
|
|
* @filesource
|
19 |
|
|
* @copyright Copyright 2005-2007, Cake Software Foundation, Inc.
|
20 |
|
|
* @link http://www.cakefoundation.org/projects/info/cakephp CakePHP(tm) Project
|
21 |
|
|
* @package cake
|
22 |
|
|
* @subpackage cake.cake.libs
|
23 |
|
|
* @since CakePHP(tm) v 0.2.9
|
24 |
|
|
* @version $Revision: 4409 $
|
25 |
|
|
* @modifiedby $LastChangedBy: phpnut $
|
26 |
|
|
* @lastmodified $Date: 2007-02-02 07:20:59 -0600 (Fri, 02 Feb 2007) $
|
27 |
|
|
* @license http://www.opensource.org/licenses/mit-license.php The MIT License
|
28 |
|
|
*/
|
29 |
|
|
/**
|
30 |
|
|
* Included libraries.
|
31 |
|
|
*
|
32 |
|
|
*/
|
33 |
|
|
if (!class_exists('Object')) {
|
34 |
|
|
uses ('object');
|
35 |
|
|
}
|
36 |
|
|
/**
|
37 |
|
|
* Text-to-HTML parser.
|
38 |
|
|
*
|
39 |
|
|
* Text-to-html parser, similar to Textile or RedCloth, only with a little different syntax.
|
40 |
|
|
*
|
41 |
|
|
* @package cake
|
42 |
|
|
* @subpackage cake.cake.libs
|
43 |
|
|
*/
|
44 |
|
|
class Flay extends Object{
|
45 |
|
|
/**
|
46 |
|
|
* Text to be parsed.
|
47 |
|
|
*
|
48 |
|
|
* @var string
|
49 |
|
|
*/
|
50 |
|
|
var $text = null;
|
51 |
|
|
/**
|
52 |
|
|
* Set this to allow HTML in the markup.
|
53 |
|
|
*
|
54 |
|
|
* @var boolean
|
55 |
|
|
*/
|
56 |
|
|
var $allow_html = false;
|
57 |
|
|
/**
|
58 |
|
|
* Constructor.
|
59 |
|
|
*
|
60 |
|
|
* @param string $text
|
61 |
|
|
*/
|
62 |
|
|
function __construct($text = null) {
|
63 |
|
|
$this->text = $text;
|
64 |
|
|
parent::__construct();
|
65 |
|
|
}
|
66 |
|
|
/**
|
67 |
|
|
* Returns given text translated to HTML using the Flay syntax.
|
68 |
|
|
*
|
69 |
|
|
* @param string $text String to format
|
70 |
|
|
* @param boolean $bare Set this to only do <p> transforms and > to >, no typography additions.
|
71 |
|
|
* @param boolean $allowHtml Set this to trim whitespace and disable all HTML
|
72 |
|
|
* @return string Formatted text
|
73 |
|
|
*/
|
74 |
|
|
function toHtml($text = null, $bare = false, $allowHtml = false) {
|
75 |
|
|
if (empty($text) && empty($this->text)) {
|
76 |
|
|
return false;
|
77 |
|
|
}
|
78 |
|
|
$text = $text ? $text : $this->text;
|
79 |
|
|
// trim whitespace and disable all HTML
|
80 |
|
|
if ($allowHtml) {
|
81 |
|
|
$text = trim($text);
|
82 |
|
|
} else {
|
83 |
|
|
$text = str_replace('<', '<', str_replace('>', '>', trim($text)));
|
84 |
|
|
}
|
85 |
|
|
|
86 |
|
|
if (!$bare) {
|
87 |
|
|
// multi-paragraph functions
|
88 |
|
|
$text=preg_replace('#(?:[\n]{0,2})"""(.*)"""(?:[\n]{0,2})#s', "\n\n%BLOCKQUOTE%\n\n\\1\n\n%ENDBLOCKQUOTE%\n\n", $text);
|
89 |
|
|
$text=preg_replace('#(?:[\n]{0,2})===(.*)===(?:[\n]{0,2})#s', "\n\n%CENTER%\n\n\\1\n\n%ENDCENTER%\n\n", $text);
|
90 |
|
|
}
|
91 |
|
|
|
92 |
|
|
// pre-parse newlines
|
93 |
|
|
$text=preg_replace("#\r\n#", "\n", $text);
|
94 |
|
|
$text=preg_replace("#[\n]{2,}#", "%PARAGRAPH%", $text);
|
95 |
|
|
$text=preg_replace('#[\n]{1}#', "%LINEBREAK%", $text);
|
96 |
|
|
$out ='';
|
97 |
|
|
|
98 |
|
|
foreach(split('%PARAGRAPH%', $text)as $line) {
|
99 |
|
|
if ($line) {
|
100 |
|
|
if (!$bare) {
|
101 |
|
|
$links = array();
|
102 |
|
|
$regs = null;
|
103 |
|
|
|
104 |
|
|
if (preg_match_all('#\[([^\[]{4,})\]#', $line, $regs)) {
|
105 |
|
|
foreach($regs[1] as $reg) {
|
106 |
|
|
$links[] = $reg;
|
107 |
|
|
$line = str_replace("[{$reg}]", '%LINK' . (count($links) - 1) . '%', $line);
|
108 |
|
|
}
|
109 |
|
|
}
|
110 |
|
|
// bold
|
111 |
|
|
$line = ereg_replace("\*([^\*]*)\*", "<strong>\\1</strong>", $line);
|
112 |
|
|
// italic
|
113 |
|
|
$line = ereg_replace("_([^_]*)_", "<em>\\1</em>", $line);
|
114 |
|
|
}
|
115 |
|
|
// entities
|
116 |
|
|
$line = str_replace(' - ', ' – ', $line);
|
117 |
|
|
$line = str_replace(' -- ', ' — ', $line);
|
118 |
|
|
$line = str_replace('(C)', '©', $line);
|
119 |
|
|
$line = str_replace('(R)', '®', $line);
|
120 |
|
|
$line = str_replace('(TM)', '™', $line);
|
121 |
|
|
// guess e-mails
|
122 |
|
|
$emails = null;
|
123 |
|
|
if (preg_match_all("#([_A-Za-z0-9+-+]+(?:\.[_A-Za-z0-9+-]+)*@[A-Za-z0-9-]+(?:\.[A-Za-z0-9-]+)*)#", $line, $emails)) {
|
124 |
|
|
foreach($emails[1] as $email) {
|
125 |
|
|
$line = str_replace($email, "<a href=\"mailto:{$email}\">{$email}</a>", $line);
|
126 |
|
|
}
|
127 |
|
|
}
|
128 |
|
|
|
129 |
|
|
if (!$bare) {
|
130 |
|
|
$urls = null;
|
131 |
|
|
if (preg_match_all("#((?:http|https|ftp|nntp)://[^ ]+)#", $line, $urls)) {
|
132 |
|
|
foreach($urls[1] as $url) {
|
133 |
|
|
$line = str_replace($url, "<a href=\"{$url}\">{$url}</a>", $line);
|
134 |
|
|
}
|
135 |
|
|
}
|
136 |
|
|
|
137 |
|
|
if (preg_match_all("#(www\.[^\n\%\ ]+[^\n\%\,\.\ ])#", $line, $urls)) {
|
138 |
|
|
foreach($urls[1] as $url) {
|
139 |
|
|
$line = str_replace($url, "<a href=\"http://{$url}\">{$url}</a>", $line);
|
140 |
|
|
}
|
141 |
|
|
}
|
142 |
|
|
|
143 |
|
|
if (count($links)) {
|
144 |
|
|
for($ii = 0; $ii < count($links); $ii++) {
|
145 |
|
|
if (preg_match("#^(http|https|ftp|nntp)://#", $links[$ii])) {
|
146 |
|
|
$prefix = null;
|
147 |
|
|
} else {
|
148 |
|
|
$prefix = 'http://';
|
149 |
|
|
}
|
150 |
|
|
if (preg_match('#^[^\ ]+\.(jpg|jpeg|gif|png)$#', $links[$ii])) {
|
151 |
|
|
$with = "<img src=\"{$prefix}{$links[$ii]}\" alt=\"\" />";
|
152 |
|
|
} elseif (preg_match('#^([^\]\ ]+)(?:\ ([^\]]+))?$#', $links[$ii], $regs)) {
|
153 |
|
|
if (isset($regs[2])) {
|
154 |
|
|
if (preg_match('#\.(jpg|jpeg|gif|png)$#', $regs[2])) {
|
155 |
|
|
$body = "<img src=\"{$prefix}{$regs[2]}\" alt=\"\" />";
|
156 |
|
|
} else {
|
157 |
|
|
$body = $regs[2];
|
158 |
|
|
}
|
159 |
|
|
} else {
|
160 |
|
|
$body = $links[$ii];
|
161 |
|
|
}
|
162 |
|
|
$with = "<a href=\"{$prefix}{$regs[1]}\" target=\"_blank\">{$body}</a>";
|
163 |
|
|
} else {
|
164 |
|
|
$with = $prefix . $links[$ii];
|
165 |
|
|
}
|
166 |
|
|
$line = str_replace("%LINK{$ii}%", $with, $line);
|
167 |
|
|
}
|
168 |
|
|
}
|
169 |
|
|
}
|
170 |
|
|
$out .= str_replace('%LINEBREAK%', "<br />\n", "<p>{$line}</p>\n");
|
171 |
|
|
}
|
172 |
|
|
}
|
173 |
|
|
|
174 |
|
|
if (!$bare) {
|
175 |
|
|
$out = str_replace('<p>%BLOCKQUOTE%</p>', "<blockquote>", $out);
|
176 |
|
|
$out = str_replace('<p>%ENDBLOCKQUOTE%</p>', "</blockquote>", $out);
|
177 |
|
|
$out = str_replace('<p>%CENTER%</p>', "<center>", $out);
|
178 |
|
|
$out = str_replace('<p>%ENDCENTER%</p>', "</center>", $out);
|
179 |
|
|
}
|
180 |
|
|
return $out;
|
181 |
|
|
}
|
182 |
|
|
/**
|
183 |
|
|
* Return the words of the string as an array.
|
184 |
|
|
*
|
185 |
|
|
* @param string $string
|
186 |
|
|
* @return array Array of words
|
187 |
|
|
*/
|
188 |
|
|
function extractWords($string) {
|
189 |
|
|
$split = preg_split('/[\s,\.:\/="!\(\)<>~\[\]]+/', $string);
|
190 |
|
|
return $split;
|
191 |
|
|
}
|
192 |
|
|
/**
|
193 |
|
|
* Return given string with words in array colorMarked, up to a number of times (defaults to 5).
|
194 |
|
|
*
|
195 |
|
|
* @param array $words Words to look for and markup
|
196 |
|
|
* @param string $string String to look in
|
197 |
|
|
* @param integer $max_snippets Max number of snippets to extract
|
198 |
|
|
* @return string
|
199 |
|
|
* @see colorMark
|
200 |
|
|
*/
|
201 |
|
|
function markedSnippets($words, $string, $max_snippets = 5) {
|
202 |
|
|
$string = strip_tags($string);
|
203 |
|
|
$snips = array();
|
204 |
|
|
$rest = $string;
|
205 |
|
|
foreach($words as $word) {
|
206 |
|
|
if (preg_match_all("/[\s,]+.{0,40}{$word}.{0,40}[\s,]+/i", $rest, $r)) {
|
207 |
|
|
foreach($r as $result) {
|
208 |
|
|
$rest = str_replace($result, '', $rest);
|
209 |
|
|
}
|
210 |
|
|
$snips = array_merge($snips, $r[0]);
|
211 |
|
|
}
|
212 |
|
|
}
|
213 |
|
|
|
214 |
|
|
if (count($snips) > $max_snippets) {
|
215 |
|
|
$snips = array_slice($snips, 0, $max_snippets);
|
216 |
|
|
}
|
217 |
|
|
$joined = join(' <b>...</b> ', $snips);
|
218 |
|
|
$snips = $joined ? "<b>...</b> {$joined} <b>...</b>" : substr($string, 0, 80) . '<b>...</b>';
|
219 |
|
|
return $this->colorMark($words, $snips);
|
220 |
|
|
}
|
221 |
|
|
/**
|
222 |
|
|
* Returns string with EM elements with color classes added.
|
223 |
|
|
*
|
224 |
|
|
* @param array $words Array of words to be colorized
|
225 |
|
|
* @param string $string Text in which the words might be found
|
226 |
|
|
* @return string
|
227 |
|
|
*/
|
228 |
|
|
function colorMark($words, $string) {
|
229 |
|
|
$colors=array('yl', 'gr', 'rd', 'bl', 'fu', 'cy');
|
230 |
|
|
$nextColorIndex = 0;
|
231 |
|
|
foreach($words as $word) {
|
232 |
|
|
$string = preg_replace("/({$word})/i", '<em class="' . $colors[$nextColorIndex % count($colors)] . "\">\\1</em>", $string);
|
233 |
|
|
$nextColorIndex++;
|
234 |
|
|
}
|
235 |
|
|
return $string;
|
236 |
|
|
}
|
237 |
|
|
/**
|
238 |
|
|
* Returns given text with tags stripped out.
|
239 |
|
|
*
|
240 |
|
|
* @param string $text
|
241 |
|
|
* @return string
|
242 |
|
|
*/
|
243 |
|
|
function toClean($text) {
|
244 |
|
|
$strip = strip_tags(html_entity_decode($text, ENT_QUOTES));
|
245 |
|
|
return $strip;
|
246 |
|
|
}
|
247 |
|
|
/**
|
248 |
|
|
* Return parsed text with tags stripped out.
|
249 |
|
|
*
|
250 |
|
|
* @param string $text
|
251 |
|
|
* @return string
|
252 |
|
|
*/
|
253 |
|
|
function toParsedAndClean($text) {
|
254 |
|
|
return $this->toClean(Flay::toHtml($text));
|
255 |
|
|
}
|
256 |
|
|
/**
|
257 |
|
|
* Return a fragment of a text, up to $length characters long, with an ellipsis after it.
|
258 |
|
|
*
|
259 |
|
|
* @param string $text Text to be truncated.
|
260 |
|
|
* @param integer $length Max length of text.
|
261 |
|
|
* @param string $ellipsis Sign to print after truncated text.
|
262 |
|
|
* @return string
|
263 |
|
|
*/
|
264 |
|
|
function fragment($text, $length, $ellipsis = '...') {
|
265 |
|
|
$soft = $length - 5;
|
266 |
|
|
$hard = $length + 5;
|
267 |
|
|
$rx = '/(.{' . $soft . ',' . $hard . '})[\s,\.:\/="!\(\)<>~\[\]]+.*/';
|
268 |
|
|
|
269 |
|
|
if (preg_match($rx, $text, $r)) {
|
270 |
|
|
$out = $r[1];
|
271 |
|
|
} else {
|
272 |
|
|
$out = substr($text, 0, $length);
|
273 |
|
|
}
|
274 |
|
|
$out = $out . (strlen($out) < strlen($text) ? $ellipsis : null);
|
275 |
|
|
return $out;
|
276 |
|
|
}
|
277 |
|
|
}
|
278 |
|
|
?>
|